Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    mathematical operators and expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    solve for variable

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    
    -0.60
    imum
    -0.45
    ohm
    -0.41
    principalTable
    -0.41
     Pand
    -0.40
     فريبيس
    -0.39
    rips
    -0.39
    "}"
    -0.39
    곧
    -0.39
    こそ
    -0.37
    POSITIVE LOGITS
     pitié
    0.54
    ChildScrollView
    0.51
     mauva
    0.51
    SourceChecksum
    0.50
     føl
    0.50
     nôtre
    0.50
     pérd
    0.49
     Gubernur
    0.47
     Comprometido
    0.47
     Infór
    0.46
    Act Density 0.415%

    No Known Activations